mathigatti / DeepSingingSynthesizer
Extension of Sinsy-NG using deep learning models for voice conversion in order to synthesize good and realistic vocals.
☆13Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for DeepSingingSynthesizer
- Python wrapper for Sinsy☆51Updated last year
- Sound examples for the Neural Parametric Singing Synthesizer (NPSS)☆22Updated 2 years ago
- DNN based singing voice synthesis☆17Updated 6 years ago
- Vocal Remover using Deep Neural Networks☆15Updated 4 months ago
- A fork of sinsy: HMM/DNN-based singing voice synthesis system☆66Updated 2 years ago
- ☆55Updated 2 years ago
- A Chinese version of A Neural Parametric Singing Synthesizer☆12Updated 2 years ago
- The Original Support for English NNSVS Dataset Creation☆25Updated last week
- Pitch Controllable DDSP Vocoders☆68Updated last week
- ☆12Updated 3 weeks ago
- singing voice conversion without f0☆22Updated last year
- PyTorch Implementation of Generalized End-to-End Loss for Speaker Verification☆28Updated 3 years ago
- ☆98Updated 2 months ago
- Official implementation of DualCycleGAN for nonparallel audio super resolution☆50Updated 2 years ago
- A minimum inference engine for DiffSinger☆34Updated 7 months ago
- MFA acoustic model training based on Opencpop☆12Updated 2 years ago
- Mellotron singing synthesizer using CPU☆13Updated last year
- ☆13Updated 11 months ago
- Vocoder NSF-HiFiGAN (Moved into deepaudio)☆49Updated last year
- singing voice conversion based on glow-tts☆11Updated last year
- Python scripts I made to make NNSVS labeling easier.☆23Updated last year
- ☆22Updated last year
- A chinese singing voice dataset, professional male singer, 105 songs, 132 minutes☆10Updated last year
- ☆22Updated last year
- SOFA_AI: Singing-Oriented Forced Aligner for Automatic Inference☆20Updated 5 months ago
- Pytorch implementation of "f0-consistent many-to-many non-parallel voice conversion via conditional autoencoder"☆28Updated 4 years ago
- ☆38Updated 2 months ago